© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 128026
    Prev
    Next
    INDEX
    Explanations

    模型类型

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    of
    0.84
    ce
    0.75
     be
    0.75
    op
    0.73
    and
    0.66
    J
    0.66
    -
    0.64
    ত
    0.63
     স
    0.62
    owanie
    0.62
    POSITIVE LOGITS
    ної
    0.76
    годи
    0.73
     for
    0.68
    იდან
    0.64
    бері
    0.63
    ھوں
    0.62
    0
    0.62
    疱
    0.61
    柢
    0.61
    наў
    0.61
    Activations Density 0.000%

    No Known Activations